tau2

Here are 3 public repositories matching this topic...

This fork of tau2-bench investigates whether LLM agent performance varies based on the temporal context of dates in prompts.

benchmark agents llm tau2

A2A-compatible Green Agent that runs τ²-bench end-to-end on AgentBeats

docker benchmark uv a2a tau2 agentbeats

Trajectory analysis framework for agent evaluation — moving beyond reward scores to behavioral explanation.

Add a description, image, and links to the tau2 topic page so that developers can more easily learn about it.

To associate your repository with the tau2 topic, visit your repo's landing page and select "manage topics."